Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/emiliaprotocol/emilia-protocolWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/emiliaprotocol/emilia-protocol/claude-code-plugin)<a href="https://agentmods.dev/plugins/emiliaprotocol/emilia-protocol/claude-code-plugin"><img src="https://agentmods.dev/badge/plugins/emiliaprotocol/emilia-protocol/claude-code-plugin/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/emiliaprotocol/emilia-protocol/claude-code-plugin"><img src="https://agentmods.dev/badge/plugins/emiliaprotocol/emilia-protocol/claude-code-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
emilia-guard scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"name": "emilia-guard",
"description": "Require a named human's signed approval before Claude does anything irreversible — money movement, destructive shell, external sends. High-risk tool calls are held until a person approves on their own device (Face ID / passkey), producing an offline-verifiable Trust Receipt. Fail-closed.",
"version": "0.1.0",
"author": { "name": "EMILIA Protocol", "url": "https://www.emiliaprotocol.ai" },
"homepage": "https://www.emiliaprotocol.ai",
"repository": "https://github.com/emiliaprotocol/emilia-protocol",
"license": "Apache-2.0",
"keywords": ["security", "human-in-the-loop", "approval", "agent-safety", "irreversible-actions", "webauthn", "audit"],
"mcpServers": {
"emilia": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@emilia-protocol/mcp-server"],
"env": {
"EP_BASE_URL": "https://www.emiliaprotocol.ai",
"EP_API_KEY": "${EP_API_KEY}"
}
}
}
}
What it installs
The manifest is a name and a version. 1 hook travel with it, and installing the plugin installs all of them. Each is measured on its own page, and each can be installed alone.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 22 lines scan A 688104127966
emilia-guard is a plugin published in the GitHub repository emiliaprotocol/emilia-protocol (611 stars, last pushed 4d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other plugins, from other repositories
boj-server
Unified Gemini extension for the BoJ (Bundle of Joy) Server infrastructure.
trustshell
AI agent security for Claude Code — read the code, break the running agent, prove it (exploit-validated). Commands: /static-scan, /red-team. Subagent: agent-red-teamer. Skills: RT-1..RT-9.
catalysis-scientist
Reasons from active-site structure, turnover frequency, selectivity, and the Sabatier principle through CO/H2 chemisorption site-counting, Weisz-Prater and Mears transport checks, Langmuir-Hinshelwood/Mars-van Krevelen kinetics, and operando DRIFTS/XAS while treating diffusion-limited apparent rates, DRIFTS spectator…
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
themes-example
themes-example. An open-source AI agent that brings the power of Gemini directly into your terminal.